summaryrefslogtreecommitdiff
path: root/lib/charset.c
blob: 10557b9e753dd39a36eda86b9fc39c6391461bc8 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
// SPDX-License-Identifier: GPL-2.0+
/*
 *  charset conversion utils
 *
 *  Copyright (c) 2017 Rob Clark
 */

#include <common.h>
#include <charset.h>
#include <capitalization.h>
#include <malloc.h>

static struct capitalization_table capitalization_table[] =
#ifdef CONFIG_EFI_UNICODE_CAPITALIZATION
	UNICODE_CAPITALIZATION_TABLE;
#elif CONFIG_FAT_DEFAULT_CODEPAGE == 1250
	CP1250_CAPITALIZATION_TABLE;
#else
	CP437_CAPITALIZATION_TABLE;
#endif

/**
 * get_code() - read Unicode code point from UTF-8 stream
 *
 * @read_u8:	- stream reader
 * @src:	- string buffer passed to stream reader, optional
 * Return:	- Unicode code point
 */
static int get_code(u8 (*read_u8)(void *data), void *data)
{
	s32 ch = 0;

	ch = read_u8(data);
	if (!ch)
		return 0;
	if (ch >= 0xc2 && ch <= 0xf4) {
		int code = 0;

		if (ch >= 0xe0) {
			if (ch >= 0xf0) {
				/* 0xf0 - 0xf4 */
				ch &= 0x07;
				code = ch << 18;
				ch = read_u8(data);
				if (ch < 0x80 || ch > 0xbf)
					goto error;
				ch &= 0x3f;
			} else {
				/* 0xe0 - 0xef */
				ch &= 0x0f;
			}
			code += ch << 12;
			if ((code >= 0xD800 && code <= 0xDFFF) ||
			    code >= 0x110000)
				goto error;
			ch = read_u8(data);
			if (ch < 0x80 || ch > 0xbf)
				goto error;
		}
		/* 0xc0 - 0xdf or continuation byte (0x80 - 0xbf) */
		ch &= 0x3f;
		code += ch << 6;
		ch = read_u8(data);
		if (ch < 0x80 || ch > 0xbf)
			goto error;
		ch &= 0x3f;
		ch += code;
	} else if (ch >= 0x80) {
		goto error;
	}
	return ch;
error:
	return '?';
}

/**
 * read_string() - read byte from character string
 *
 * @data:	- pointer to string
 * Return:	- byte read
 *
 * The string pointer is incremented if it does not point to '\0'.
 */
static u8 read_string(void *data)

{
	const char **src = (const char **)data;
	u8 c;

	if (!src || !*src || !**src)
		return 0;
	c = **src;
	++*src;
	return c;
}

/**
 * read_console() - read byte from console
 *
 * @data	- not used, needed to match interface
 * Return:	- byte read or 0 on error
 */
static u8 read_console(void *data)
{
	int ch;

	ch = getc();
	if (ch < 0)
		ch = 0;
	return ch;
}

int console_read_unicode(s32 *code)
{
	if (!tstc()) {
		/* No input available */
		return 1;
	}

	/* Read Unicode code */
	*code = get_code(read_console, NULL);
	return 0;
}

s32 utf8_get(const char **src)
{
	return get_code(read_string, src);
}

int utf8_put(s32 code, char **dst)
{
	if (!dst || !*dst)
		return -1;
	if ((code >= 0xD800 && code <= 0xDFFF) || code >= 0x110000)
		return -1;
	if (code <= 0x007F) {
		**dst = code;
	} else {
		if (code <= 0x07FF) {
			**dst = code >> 6 | 0xC0;
		} else {
			if (code < 0x10000) {
				**dst = code >> 12 | 0xE0;
			} else {
				**dst = code >> 18 | 0xF0;
				++*dst;
				**dst = (code >> 12 & 0x3F) | 0x80;
			}
			++*dst;
			**dst = (code >> 6 & 0x3F) | 0x80;
		}
		++*dst;
		**dst = (code & 0x3F) | 0x80;
	}
	++*dst;
	return 0;
}

size_t utf8_utf16_strnlen(const char *src, size_t count)
{
	size_t len = 0;

	for (; *src && count; --count)  {
		s32 code = utf8_get(&src);

		if (!code)
			break;
		if (code < 0) {
			/* Reserve space for a replacement character */
			len += 1;
		} else if (code < 0x10000) {
			len += 1;
		} else {
			len += 2;
		}
	}
	return len;
}

int utf8_utf16_strncpy(u16 **dst, const char *src, size_t count)
{
	if (!src || !dst || !*dst)
		return -1;

	for (; count && *src; --count) {
		s32 code = utf8_get(&src);

		if (code < 0)
			code = '?';
		utf16_put(code, dst);
	}
	**dst = 0;
	return 0;
}

s32 utf16_get(const u16 **src)
{
	s32 code, code2;

	if (!src || !*src)
		return -1;
	if (!**src)
		return 0;
	code = **src;
	++*src;
	if (code >= 0xDC00 && code <= 0xDFFF)
		return -1;
	if (code >= 0xD800 && code <= 0xDBFF) {
		if (!**src)
			return -1;
		code &= 0x3ff;
		code <<= 10;
		code += 0x10000;
		code2 = **src;
		++*src;
		if (code2 <= 0xDC00 || code2 >= 0xDFFF)
			return -1;
		code2 &= 0x3ff;
		code += code2;
	}
	return code;
}

int utf16_put(s32 code, u16 **dst)
{
	if (!dst || !*dst)
		return -1;
	if ((code >= 0xD800 && code <= 0xDFFF) || code >= 0x110000)
		return -1;
	if (code < 0x10000) {
		**dst = code;
	} else {
		code -= 0x10000;
		**dst = code >> 10 | 0xD800;
		++*dst;
		**dst = (code & 0x3ff) | 0xDC00;
	}
	++*dst;
	return 0;
}

size_t utf16_strnlen(const u16 *src, size_t count)
{
	size_t len = 0;

	for (; *src && count; --count)  {
		s32 code = utf16_get(&src);

		if (!code)
			break;
		/*
		 * In case of an illegal sequence still reserve space for a
		 * replacement character.
		 */
		++len;
	}
	return len;
}

size_t utf16_utf8_strnlen(const u16 *src, size_t count)
{
	size_t len = 0;

	for (; *src && count; --count)  {
		s32 code = utf16_get(&src);

		if (!code)
			break;
		if (code < 0)
			/* Reserve space for a replacement character */
			len += 1;
		else if (code < 0x80)
			len += 1;
		else if (code < 0x800)
			len += 2;
		else if (code < 0x10000)
			len += 3;
		else
			len += 4;
	}
	return len;
}

int utf16_utf8_strncpy(char **dst, const u16 *src, size_t count)
{
	if (!src || !dst || !*dst)
		return -1;

	for (; count && *src; --count) {
		s32 code = utf16_get(&src);

		if (code < 0)
			code = '?';
		utf8_put(code, dst);
	}
	**dst = 0;
	return 0;
}

s32 utf_to_lower(const s32 code)
{
	struct capitalization_table *pos = capitalization_table;
	s32 ret = code;

	if (code <= 0x7f) {
		if (code >= 'A' && code <= 'Z')
			ret += 0x20;
		return ret;
	}
	for (; pos->upper; ++pos) {
		if (pos->upper == code) {
			ret = pos->lower;
			break;
		}
	}
	return ret;
}

s32 utf_to_upper(const s32 code)
{
	struct capitalization_table *pos = capitalization_table;
	s32 ret = code;

	if (code <= 0x7f) {
		if (code >= 'a' && code <= 'z')
			ret -= 0x20;
		return ret;
	}
	for (; pos->lower; ++pos) {
		if (pos->lower == code) {
			ret = pos->upper;
			break;
		}
	}
	return ret;
}

size_t u16_strlen(const u16 *in)
{
	size_t i;
	for (i = 0; in[i]; i++);
	return i;
}

size_t u16_strnlen(const u16 *in, size_t count)
{
	size_t i;
	for (i = 0; count-- && in[i]; i++);
	return i;
}

/* Convert UTF-16 to UTF-8.  */
uint8_t *utf16_to_utf8(uint8_t *dest, const uint16_t *src, size_t size)
{
	uint32_t code_high = 0;

	while (size--) {
		uint32_t code = *src++;

		if (code_high) {
			if (code >= 0xDC00 && code <= 0xDFFF) {
				/* Surrogate pair.  */
				code = ((code_high - 0xD800) << 10) + (code - 0xDC00) + 0x10000;

				*dest++ = (code >> 18) | 0xF0;
				*dest++ = ((code >> 12) & 0x3F) | 0x80;
				*dest++ = ((code >> 6) & 0x3F) | 0x80;
				*dest++ = (code & 0x3F) | 0x80;
			} else {
				/* Error...  */
				*dest++ = '?';
				/* *src may be valid. Don't eat it.  */
				src--;
			}

			code_high = 0;
		} else {
			if (code <= 0x007F) {
				*dest++ = code;
			} else if (code <= 0x07FF) {
				*dest++ = (code >> 6) | 0xC0;
				*dest++ = (code & 0x3F) | 0x80;
			} else if (code >= 0xD800 && code <= 0xDBFF) {
				code_high = code;
				continue;
			} else if (code >= 0xDC00 && code <= 0xDFFF) {
				/* Error... */
				*dest++ = '?';
			} else if (code < 0x10000) {
				*dest++ = (code >> 12) | 0xE0;
				*dest++ = ((code >> 6) & 0x3F) | 0x80;
				*dest++ = (code & 0x3F) | 0x80;
			} else {
				*dest++ = (code >> 18) | 0xF0;
				*dest++ = ((code >> 12) & 0x3F) | 0x80;
				*dest++ = ((code >> 6) & 0x3F) | 0x80;
				*dest++ = (code & 0x3F) | 0x80;
			}
		}
	}

	return dest;
}